Theory

Efficient Neural Network Verification with Exactness Characterization UAI 2019 Energy and Policy Considerations for Deep Learning in NLP ACL 2019 Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets NeurIPS 2019 Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression CVPR 2019 Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias NeurIPS 2019 Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks ICML 2019 Fisher-Rao Metric, Geometry, and Complexity of Neural Networks AISTATS 2019 Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the Hamming Distance IJCAI 2019 Gradient descent aligns the layers of deep linear networks ICLR 2019 Gradient Dynamics of Shallow Univariate ReLU Networks NeurIPS 2019 How do infinite width bounded norm networks look in function space? COLT 2019 Implicit Regularization for Optimal Sparse Recovery NeurIPS 2019 Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks NeurIPS 2019 Initialization of ReLUs for Dynamical Isometry NeurIPS 2019 Inverse Abstraction of Neural Networks Using Symbolic Interpolation AAAI 2019 Inverse Path Tracing for Joint Material and Lighting Estimation CVPR 2019 Learnability for the Information Bottleneck UAI 2019 Learning Adaptive Random Features AAAI 2019 Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks NeurIPS 2019 Limitations of the empirical Fisher approximation for natural gradient descent NeurIPS 2019 Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit COLT 2019 ODE-Inspired Network Design for Single Image Super-Resolution CVPR 2019 On Exact Computation with an Infinitely Wide Neural Net NeurIPS 2019 On NMT Search Errors and Model Errors: Cat Got Your Tongue? EMNLP 2019 On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition AISTATS 2019